From: Borislav Petkov <bp@suse.de>
Unify the bank preparation into __mcheck_cpu_init_clear_banks(), rename
that function to what it does now - prepares banks. Do this so that
generic and vendor banks init goes first so that settings done during
that init can take effect before the first bank polling takes place.
Move __mcheck_cpu_check_banks() into __mcheck_cpu_init_prepare_banks()
as it already loops over the banks.
The MCP_DONTLOG flag is no longer needed, since the MCA polling function
is now called only if boot-time logging should be done.
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
---
Notes:
Link:
https://lore.kernel.org/r/20250624-wip-mca-updates-v4-9-236dd74f645f@amd.com
v4->v5:
* No change.
v3->v4:
* No change.
v2->v3:
* Update commit message.
* Add tags from Qiuxu and Tony.
v1->v2:
* New in v2, but based on old patch (see link).
* Kept old tags for reference.
arch/x86/include/asm/mce.h | 3 +-
arch/x86/kernel/cpu/mce/core.c | 63 ++++++++++++------------------------------
2 files changed, 19 insertions(+), 47 deletions(-)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 752802bf966b..3224f3862dc8 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -290,8 +290,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
enum mcp_flags {
MCP_TIMESTAMP = BIT(0), /* log time stamp */
MCP_UC = BIT(1), /* log uncorrected errors */
- MCP_DONTLOG = BIT(2), /* only clear, don't log */
- MCP_QUEUE_LOG = BIT(3), /* only queue to genpool */
+ MCP_QUEUE_LOG = BIT(2), /* only queue to genpool */
};
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4da4eab56c81..311876e3f3f4 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -807,9 +807,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
continue;
log_it:
- if (flags & MCP_DONTLOG)
- goto clear_it;
-
mce_read_aux(&err, i);
m->severity = mce_severity(m, NULL, NULL, false);
/*
@@ -1812,7 +1809,7 @@ static void __mcheck_cpu_mce_banks_init(void)
/*
* Init them all, __mcheck_cpu_apply_quirks() is going to apply
* the required vendor quirks before
- * __mcheck_cpu_init_clear_banks() does the final bank setup.
+ * __mcheck_cpu_init_prepare_banks() does the final bank setup.
*/
b->ctl = -1ULL;
b->init = true;
@@ -1851,21 +1848,8 @@ static void __mcheck_cpu_cap_init(void)
static void __mcheck_cpu_init_generic(void)
{
- enum mcp_flags m_fl = 0;
- mce_banks_t all_banks;
u64 cap;
- if (!mca_cfg.bootlog)
- m_fl = MCP_DONTLOG;
-
- /*
- * Log the machine checks left over from the previous reset. Log them
- * only, do not start processing them. That will happen in mcheck_late_init()
- * when all consumers have been registered on the notifier chain.
- */
- bitmap_fill(all_banks, MAX_NR_BANKS);
- machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks);
-
cr4_set_bits(X86_CR4_MCE);
rdmsrq(MSR_IA32_MCG_CAP, cap);
@@ -1873,36 +1857,23 @@ static void __mcheck_cpu_init_generic(void)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
}
-static void __mcheck_cpu_init_clear_banks(void)
+static void __mcheck_cpu_init_prepare_banks(void)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+ u64 msrval;
int i;
- for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
- struct mce_bank *b = &mce_banks[i];
+ /*
+ * Log the machine checks left over from the previous reset. Log them
+ * only, do not start processing them. That will happen in mcheck_late_init()
+ * when all consumers have been registered on the notifier chain.
+ */
+ if (mca_cfg.bootlog) {
+ mce_banks_t all_banks;
- if (!b->init)
- continue;
- wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
- wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
+ bitmap_fill(all_banks, MAX_NR_BANKS);
+ machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
}
-}
-
-/*
- * Do a final check to see if there are any unused/RAZ banks.
- *
- * This must be done after the banks have been initialized and any quirks have
- * been applied.
- *
- * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs.
- * Otherwise, a user who disables a bank will not be able to re-enable it
- * without a system reboot.
- */
-static void __mcheck_cpu_check_banks(void)
-{
- struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
- u64 msrval;
- int i;
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
struct mce_bank *b = &mce_banks[i];
@@ -1910,6 +1881,9 @@ static void __mcheck_cpu_check_banks(void)
if (!b->init)
continue;
+ wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
+ wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
+
rdmsrq(mca_msr_reg(i, MCA_CTL), msrval);
b->init = !!msrval;
}
@@ -2314,8 +2288,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_init_early(c);
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
- __mcheck_cpu_init_clear_banks();
- __mcheck_cpu_check_banks();
+ __mcheck_cpu_init_prepare_banks();
__mcheck_cpu_setup_timer();
}
@@ -2483,7 +2456,7 @@ static void mce_syscore_resume(void)
{
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
- __mcheck_cpu_init_clear_banks();
+ __mcheck_cpu_init_prepare_banks();
}
static struct syscore_ops mce_syscore_ops = {
@@ -2501,7 +2474,7 @@ static void mce_cpu_restart(void *data)
if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
- __mcheck_cpu_init_clear_banks();
+ __mcheck_cpu_init_prepare_banks();
__mcheck_cpu_init_timer();
}
--
2.51.0On Mon, Aug 25, 2025 at 05:33:02PM +0000, Yazen Ghannam wrote:
> From: Borislav Petkov <bp@suse.de>
>
> Unify the bank preparation into __mcheck_cpu_init_clear_banks(), rename
> that function to what it does now - prepares banks. Do this so that
> generic and vendor banks init goes first so that settings done during
> that init can take effect before the first bank polling takes place.
>
> Move __mcheck_cpu_check_banks() into __mcheck_cpu_init_prepare_banks()
> as it already loops over the banks.
>
> The MCP_DONTLOG flag is no longer needed, since the MCA polling function
> is now called only if boot-time logging should be done.
>
> Signed-off-by: Borislav Petkov <bp@suse.de>
Yeah, when you send someone else's patch, you need to add your SOB underneath.
I'll add it now.
> Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
> Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
> Tested-by: Tony Luck <tony.luck@intel.com>
> Reviewed-by: Tony Luck <tony.luck@intel.com>
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
On Tue, Aug 26, 2025 at 02:35:03PM +0200, Borislav Petkov wrote: > On Mon, Aug 25, 2025 at 05:33:02PM +0000, Yazen Ghannam wrote: > > From: Borislav Petkov <bp@suse.de> > > > > Unify the bank preparation into __mcheck_cpu_init_clear_banks(), rename > > that function to what it does now - prepares banks. Do this so that > > generic and vendor banks init goes first so that settings done during > > that init can take effect before the first bank polling takes place. > > > > Move __mcheck_cpu_check_banks() into __mcheck_cpu_init_prepare_banks() > > as it already loops over the banks. > > > > The MCP_DONTLOG flag is no longer needed, since the MCA polling function > > is now called only if boot-time logging should be done. > > > > Signed-off-by: Borislav Petkov <bp@suse.de> > > Yeah, when you send someone else's patch, you need to add your SOB underneath. > I'll add it now. Thanks. Sorry I didn't think of it that way, since it was posted to the mailing list and I was just including it. I was thinking SOB was for submitting on another person's behalf. But I see how any inclusion counts: "Any further SoBs (Signed-off-by:'s) following the author's SoB are from people handling and transporting the patch..." Thanks again. -Yazen
On Tue, Aug 26, 2025 at 09:47:54AM -0400, Yazen Ghannam wrote:
> But I see how any inclusion counts:
> "Any further SoBs (Signed-off-by:'s) following the author's SoB are from
> people handling and transporting the patch..."
Yeah, that's the important point: each patch's SOB must document the path it
took from the author to the upstream kernel. That's why people who forward it
by adding it to their set or whatever else, must add their SOB for documenting
that they handled it on its way. Basically.
Thx.
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
The following commit has been merged into the ras/core branch of tip:
Commit-ID: 0f134c53246366c00664b640f9edc9be5db255b3
Gitweb: https://git.kernel.org/tip/0f134c53246366c00664b640f9edc9be5db255b3
Author: Borislav Petkov <bp@suse.de>
AuthorDate: Mon, 25 Aug 2025 17:33:02
Committer: Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Fri, 05 Sep 2025 12:42:55 +02:00
x86/mce: Cleanup bank processing on init
Unify the bank preparation into __mcheck_cpu_init_clear_banks(), rename that
function to what it does now - prepares banks. Do this so that generic and
vendor banks init goes first so that settings done during that init can take
effect before the first bank polling takes place.
Move __mcheck_cpu_check_banks() into __mcheck_cpu_init_prepare_banks() as it
already loops over the banks.
The MCP_DONTLOG flag is no longer needed, since the MCA polling function is
now called only if boot-time logging should be done.
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250825-wip-mca-updates-v5-5-865768a2eef8@amd.com
---
arch/x86/include/asm/mce.h | 3 +--
arch/x86/kernel/cpu/mce/core.c | 63 +++++++++------------------------
2 files changed, 19 insertions(+), 47 deletions(-)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 752802b..3224f38 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -290,8 +290,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
enum mcp_flags {
MCP_TIMESTAMP = BIT(0), /* log time stamp */
MCP_UC = BIT(1), /* log uncorrected errors */
- MCP_DONTLOG = BIT(2), /* only clear, don't log */
- MCP_QUEUE_LOG = BIT(3), /* only queue to genpool */
+ MCP_QUEUE_LOG = BIT(2), /* only queue to genpool */
};
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4da4eab..311876e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -807,9 +807,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
continue;
log_it:
- if (flags & MCP_DONTLOG)
- goto clear_it;
-
mce_read_aux(&err, i);
m->severity = mce_severity(m, NULL, NULL, false);
/*
@@ -1812,7 +1809,7 @@ static void __mcheck_cpu_mce_banks_init(void)
/*
* Init them all, __mcheck_cpu_apply_quirks() is going to apply
* the required vendor quirks before
- * __mcheck_cpu_init_clear_banks() does the final bank setup.
+ * __mcheck_cpu_init_prepare_banks() does the final bank setup.
*/
b->ctl = -1ULL;
b->init = true;
@@ -1851,21 +1848,8 @@ static void __mcheck_cpu_cap_init(void)
static void __mcheck_cpu_init_generic(void)
{
- enum mcp_flags m_fl = 0;
- mce_banks_t all_banks;
u64 cap;
- if (!mca_cfg.bootlog)
- m_fl = MCP_DONTLOG;
-
- /*
- * Log the machine checks left over from the previous reset. Log them
- * only, do not start processing them. That will happen in mcheck_late_init()
- * when all consumers have been registered on the notifier chain.
- */
- bitmap_fill(all_banks, MAX_NR_BANKS);
- machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks);
-
cr4_set_bits(X86_CR4_MCE);
rdmsrq(MSR_IA32_MCG_CAP, cap);
@@ -1873,36 +1857,23 @@ static void __mcheck_cpu_init_generic(void)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
}
-static void __mcheck_cpu_init_clear_banks(void)
+static void __mcheck_cpu_init_prepare_banks(void)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+ u64 msrval;
int i;
- for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
- struct mce_bank *b = &mce_banks[i];
+ /*
+ * Log the machine checks left over from the previous reset. Log them
+ * only, do not start processing them. That will happen in mcheck_late_init()
+ * when all consumers have been registered on the notifier chain.
+ */
+ if (mca_cfg.bootlog) {
+ mce_banks_t all_banks;
- if (!b->init)
- continue;
- wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
- wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
+ bitmap_fill(all_banks, MAX_NR_BANKS);
+ machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
}
-}
-
-/*
- * Do a final check to see if there are any unused/RAZ banks.
- *
- * This must be done after the banks have been initialized and any quirks have
- * been applied.
- *
- * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs.
- * Otherwise, a user who disables a bank will not be able to re-enable it
- * without a system reboot.
- */
-static void __mcheck_cpu_check_banks(void)
-{
- struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
- u64 msrval;
- int i;
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
struct mce_bank *b = &mce_banks[i];
@@ -1910,6 +1881,9 @@ static void __mcheck_cpu_check_banks(void)
if (!b->init)
continue;
+ wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
+ wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
+
rdmsrq(mca_msr_reg(i, MCA_CTL), msrval);
b->init = !!msrval;
}
@@ -2314,8 +2288,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_init_early(c);
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
- __mcheck_cpu_init_clear_banks();
- __mcheck_cpu_check_banks();
+ __mcheck_cpu_init_prepare_banks();
__mcheck_cpu_setup_timer();
}
@@ -2483,7 +2456,7 @@ static void mce_syscore_resume(void)
{
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
- __mcheck_cpu_init_clear_banks();
+ __mcheck_cpu_init_prepare_banks();
}
static struct syscore_ops mce_syscore_ops = {
@@ -2501,7 +2474,7 @@ static void mce_cpu_restart(void *data)
if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
- __mcheck_cpu_init_clear_banks();
+ __mcheck_cpu_init_prepare_banks();
__mcheck_cpu_init_timer();
}
© 2016 - 2025 Red Hat, Inc.